Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     từng
    -0.07
     заступ
    -0.07
     Hàng
    -0.06
    setDefault
    -0.06
    омі
    -0.06
     Streets
    -0.06
    也有
    -0.06
    Writes
    -0.06
     consectetur
    -0.06
     political
    -0.06
    POSITIVE LOGITS
     사건
    0.07
    _SEQ
    0.06
    love
    0.06
    athom
    0.06
    法律
    0.06
    �
    0.06
     Vampire
    0.06
     увагу
    0.06
    аний
    0.06
    checker
    0.06
    Act Density 0.020%

    No Known Activations